load required functions and packages:

source("sc_func.R")
suppressMessages(library(Rtsne))
suppressMessages(library(destiny))
suppressMessages(library(ggplot2))
suppressMessages(library(gplots))
suppressMessages(library(RColorBrewer))

load the data

load("sc_192.RData")
head(ph_data)
##                    CD16.32     CD11b     CD135     CD127     CD150
## AGCGTCAT_AACAGCTC 982.3378 179.57397  245.2390  337.2304 156.07208
## AGCGTCAT_AACTCCAG 407.4659 190.37300  157.5722  727.4041 376.21133
## AGCGTCAT_AAGCCGTT 559.6830  50.00000  358.8045  274.8067  99.28712
## AGCGTCAT_AAGCTCTG 507.7003  99.29826  620.0193  224.3781  50.00000
## AGCGTCAT_ACACTGCA 674.4346  55.30264  843.7025  385.0173  55.13793
## AGCGTCAT_ACATGTCG 171.7648  50.00000 2537.2556 1241.0624  87.76251
##                       Sca.1      cKit
## AGCGTCAT_AACAGCTC  624.7090 10275.788
## AGCGTCAT_AACTCCAG  681.1675  9301.442
## AGCGTCAT_AAGCCGTT 3592.4006  6043.179
## AGCGTCAT_AAGCTCTG 2009.3131 10690.092
## AGCGTCAT_ACACTGCA 1903.8698  5888.153
## AGCGTCAT_ACATGTCG  996.0054  5305.947
expr_data[1:5,1:5]
##       AGCGTCAT_AACAGCTC AGCGTCAT_AACTCCAG AGCGTCAT_AAGCCGTT
## Gnai3         19.298142           1.88219          4.365135
## Cdc45          3.216357           1.88219          0.000000
## Scml2          0.000000           0.00000          0.000000
## Narf           3.216357           0.00000          4.365135
## Cav2           0.000000           0.00000          0.000000
##       AGCGTCAT_AAGCTCTG AGCGTCAT_ACACTGCA
## Gnai3          0.000000          5.627223
## Cdc45          4.061281          2.813611
## Scml2          0.000000          0.000000
## Narf           0.000000          0.000000
## Cav2           0.000000          0.000000
dim(expr_data)
## [1] 10017   187
plot(pca_out,n=20)

batch = rep(0,nrow(pca_out$x))
batch[grep("AGCGTCAT_",rownames(pca_out$x))] = 1
batch = as.factor(batch)
plot(pca_out$x[,1],pca_out$x[,2], col=batch)

plot(pca_out$x[,1],pca_out$x[,3], col=batch)

plot(pca_out$x[,1],pca_out$x[,4], col=batch)

plot(pca_out$x[,1],pca_out$x[,5], col=batch)

plot(pca_out$x[,3],pca_out$x[,4], col=batch)

for (i in 1:10)
{
  print(paste("PCA@@@dimesion:",i))
  print(head(pca_GO_list[[i]]))
}
## [1] "PCA@@@dimesion: 1"
##        GO.ID                                        Term Annotated
## 1 GO:0006259                       DNA metabolic process       631
## 2 GO:0006260                             DNA replication       231
## 3 GO:0006261               DNA-dependent DNA replication        90
## 4 GO:0006139 nucleobase-containing compound metabolic...      3201
## 5 GO:0006725 cellular aromatic compound metabolic pro...      3277
## 6 GO:0046483               heterocycle metabolic process      3278
##   Significant Expected classic
## 1          27     3.20 7.7e-20
## 2          19     1.17 7.6e-19
## 3          13     0.46 3.3e-16
## 4          43    16.25 2.8e-15
## 5          43    16.64 7.2e-15
## 6          43    16.64 7.3e-15
## [1] "PCA@@@dimesion: 2"
##        GO.ID                                        Term Annotated
## 1 GO:0044707       single-multicellular organism process      2630
## 2 GO:0032501            multicellular organismal process      2790
## 3 GO:0006357 regulation of transcription from RNA pol...      1021
## 4 GO:0048518 positive regulation of biological proces...      2894
## 5 GO:0006366 transcription from RNA polymerase II pro...      1067
## 6 GO:0060348                            bone development        82
##   Significant Expected classic
## 1          29    13.63 4.5e-06
## 2          29    14.45 1.6e-05
## 3          16     5.29 3.3e-05
## 4          29    14.99 3.4e-05
## 5          16     5.53 5.7e-05
## 6           5     0.42 6.1e-05
## [1] "PCA@@@dimesion: 3"
##        GO.ID                                        Term Annotated
## 1 GO:0044707       single-multicellular organism process      2630
## 2 GO:0032501            multicellular organismal process      2790
## 3 GO:0001775                             cell activation       486
## 4 GO:0007275          multicellular organism development      2208
## 5 GO:0030097                                 hemopoiesis       488
## 6 GO:0048534 hematopoietic or lymphoid organ developm...       513
##   Significant Expected classic
## 1          34    13.35 9.0e-10
## 2          34    14.17 4.9e-09
## 3          15     2.47 8.8e-09
## 4          30    11.21 9.0e-09
## 5          15     2.48 9.4e-09
## 6          15     2.60 1.8e-08
## [1] "PCA@@@dimesion: 4"
##        GO.ID                                        Term Annotated
## 1 GO:0019886 antigen processing and presentation of e...        12
## 2 GO:0034341                response to interferon-gamma        38
## 3 GO:0021846             cell proliferation in forebrain        14
## 4 GO:0002495 antigen processing and presentation of p...        15
## 5 GO:0002504 antigen processing and presentation of p...        15
## 6 GO:0002478 antigen processing and presentation of e...        22
##   Significant Expected classic
## 1           3     0.06 2.5e-05
## 2           4     0.19 3.5e-05
## 3           3     0.07 4.0e-05
## 4           3     0.07 5.0e-05
## 5           3     0.07 5.0e-05
## 6           3     0.11 1.7e-04
## [1] "PCA@@@dimesion: 5"
##        GO.ID                           Term Annotated Significant Expected
## 1 GO:0002376          immune system process      1160          17     5.65
## 2 GO:0050832     defense response to fungus        12           3     0.06
## 3 GO:1903706      regulation of hemopoiesis       211           7     1.03
## 4 GO:0009620             response to fungus        20           3     0.10
## 5 GO:0072009 nephron epithelium development        25           3     0.12
## 6 GO:0009605  response to external stimulus       912          13     4.44
##   classic
## 1 1.6e-05
## 2 2.3e-05
## 3 6.5e-05
## 4 1.2e-04
## 5 2.3e-04
## 6 2.9e-04
## [1] "PCA@@@dimesion: 6"
##        GO.ID               Term Annotated Significant Expected classic
## 1 GO:0000280   nuclear division       393           9     2.00 0.00014
## 2 GO:0007049         cell cycle      1080          15     5.48 0.00019
## 3 GO:0048285  organelle fission       422           9     2.14 0.00023
## 4 GO:0051301      cell division       448           9     2.27 0.00036
## 5 GO:0051321 meiotic cell cycle       124           5     0.63 0.00039
## 6 GO:0022402 cell cycle process       782          12     3.97 0.00041
## [1] "PCA@@@dimesion: 7"
##        GO.ID                                        Term Annotated
## 1 GO:0032606                type I interferon production        48
## 2 GO:0032481 positive regulation of type I interferon...        33
## 3 GO:0071621                      granulocyte chemotaxis        39
## 4 GO:0060326                             cell chemotaxis        93
## 5 GO:0032479 regulation of type I interferon producti...        45
## 6 GO:0097530                       granulocyte migration        45
##   Significant Expected classic
## 1           4     0.25 0.00010
## 2           3     0.17 0.00064
## 3           3     0.20 0.00105
## 4           4     0.48 0.00133
## 5           3     0.23 0.00159
## 6           3     0.23 0.00159
## [1] "PCA@@@dimesion: 8"
##        GO.ID                                 Term Annotated Significant
## 1 GO:0016569      covalent chromatin modification       337          10
## 2 GO:0016570                 histone modification       331           9
## 3 GO:0016568               chromatin modification       458          10
## 4 GO:0006325               chromatin organization       494          10
## 5 GO:1903308 regulation of chromatin modification       114           5
## 6 GO:1902275 regulation of chromatin organization       121           5
##   Expected classic
## 1     1.68 4.7e-06
## 2     1.65 3.0e-05
## 3     2.28 6.8e-05
## 4     2.46 1.3e-04
## 5     0.57 2.4e-04
## 6     0.60 3.2e-04
## [1] "PCA@@@dimesion: 9"
##        GO.ID                                        Term Annotated
## 1 GO:0051240 positive regulation of multicellular org...       707
## 2 GO:0044707       single-multicellular organism process      2630
## 3 GO:0001817           regulation of cytokine production       296
## 4 GO:0048731                          system development      1925
## 5 GO:0032501            multicellular organismal process      2790
## 6 GO:0048513                    animal organ development      1390
##   Significant Expected classic
## 1          13     3.44 2.1e-05
## 2          26    12.81 4.4e-05
## 3           8     1.44 7.9e-05
## 4          21     9.37 1.0e-04
## 5          26    13.59 1.3e-04
## 6          17     6.77 1.7e-04
## [1] "PCA@@@dimesion: 10"
##        GO.ID                                   Term Annotated Significant
## 1 GO:0071496 cellular response to external stimulus       117           5
## 2 GO:0009267        cellular response to starvation        78           4
## 3 GO:0042594                 response to starvation        87           4
## 4 GO:0032835                 glomerulus development        11           2
## 5 GO:0035994             response to muscle stretch        11           2
## 6 GO:0031669   cellular response to nutrient levels        95           4
##   Expected classic
## 1     0.61 0.00033
## 2     0.40 0.00069
## 3     0.45 0.00103
## 4     0.06 0.00140
## 5     0.06 0.00140
## 6     0.49 0.00144
dif <- DiffusionMap( pca_out$x[,c(2,3,5,7,8,9,10,11,12,13,14)],n.eigs = 10)
#plot(dif)
plot(dif@eigenvectors[,1],dif@eigenvectors[,2])

plot(dif@eigenvectors[,1],dif@eigenvectors[,3])

plot(dif@eigenvectors[,1],dif@eigenvectors[,4])

plot(dif@eigenvectors[,2],dif@eigenvectors[,3])

for (i in 1:10)
{
  print(paste("diffusion map @@@dimension:",i))
  print(dif_GO_list$GO_enrich[[i]])
}
## [1] "diffusion map @@@dimension: 1"
##         GO.ID                                        Term Annotated
## 1  GO:0048821                     erythrocyte development        25
## 2  GO:0030218                 erythrocyte differentiation        86
## 3  GO:0034101                     erythrocyte homeostasis        93
## 4  GO:0061515                    myeloid cell development        48
## 5  GO:0002262                    myeloid cell homeostasis       111
## 6  GO:0048872              homeostasis of number of cells       199
## 7  GO:0001764                            neuron migration        71
## 8  GO:0006929          substrate-dependent cell migration        12
## 9  GO:0019886 antigen processing and presentation of e...        12
## 10 GO:0002495 antigen processing and presentation of p...        15
##    Significant Expected classic
## 1            6     0.22 5.2e-08
## 2            8     0.74 6.5e-07
## 3            8     0.80 1.2e-06
## 4            6     0.41 3.1e-06
## 5            8     0.95 4.6e-06
## 6           10     1.71 7.3e-06
## 7            6     0.61 3.1e-05
## 8            3     0.10 1.3e-04
## 9            3     0.10 1.3e-04
## 10           3     0.13 2.6e-04
## [1] "diffusion map @@@dimension: 2"
##         GO.ID                                        Term Annotated
## 1  GO:0048513                    animal organ development      1390
## 2  GO:0044707       single-multicellular organism process      2630
## 3  GO:0048731                          system development      1925
## 4  GO:0007275          multicellular organism development      2208
## 5  GO:0030097                                 hemopoiesis       488
## 6  GO:0032501            multicellular organismal process      2790
## 7  GO:0048534 hematopoietic or lymphoid organ developm...       513
## 8  GO:0030154                        cell differentiation      1744
## 9  GO:0002520                   immune system development       544
## 10 GO:0051240 positive regulation of multicellular org...       707
##    Significant Expected classic
## 1           42    13.83 2.8e-12
## 2           57    26.16 3.3e-11
## 3           48    19.15 3.7e-11
## 4           51    21.96 1.0e-10
## 5           23     4.85 2.5e-10
## 6           57    27.75 4.2e-10
## 7           23     5.10 6.8e-10
## 8           43    17.35 1.2e-09
## 9           23     5.41 2.1e-09
## 10          26     7.03 2.9e-09
## [1] "diffusion map @@@dimension: 3"
##         GO.ID                                        Term Annotated
## 1  GO:0002376                       immune system process      1160
## 2  GO:0044130 negative regulation of growth of symbion...        12
## 3  GO:0044146 negative regulation of growth of symbion...        12
## 4  GO:0044126    regulation of growth of symbiont in host        13
## 5  GO:0044144 modulation of growth of symbiont involve...        13
## 6  GO:0001909             leukocyte mediated cytotoxicity        50
## 7  GO:0006952                            defense response       612
## 8  GO:0044110    growth involved in symbiotic interaction        15
## 9  GO:0044116 growth of symbiont involved in interacti...        15
## 10 GO:0044117                  growth of symbiont in host        15
##    Significant Expected classic
## 1           27    10.58 2.4e-06
## 2            4     0.11 3.0e-06
## 3            4     0.11 3.0e-06
## 4            4     0.12 4.3e-06
## 5            4     0.12 4.3e-06
## 6            6     0.46 5.6e-06
## 7           18     5.58 7.9e-06
## 8            4     0.14 8.2e-06
## 9            4     0.14 8.2e-06
## 10           4     0.14 8.2e-06
## [1] "diffusion map @@@dimension: 4"
##         GO.ID                                        Term Annotated
## 1  GO:0048821                     erythrocyte development        25
## 2  GO:0030218                 erythrocyte differentiation        86
## 3  GO:0034097                        response to cytokine       294
## 4  GO:0034101                     erythrocyte homeostasis        93
## 5  GO:0061515                    myeloid cell development        48
## 6  GO:0002262                    myeloid cell homeostasis       111
## 7  GO:0048568                 embryonic organ development       211
## 8  GO:0002720 positive regulation of cytokine producti...        18
## 9  GO:0048513                    animal organ development      1390
## 10 GO:0048534 hematopoietic or lymphoid organ developm...       513
##    Significant Expected classic
## 1            6     0.21 4.9e-08
## 2            8     0.73 6.0e-07
## 3           13     2.50 1.0e-06
## 4            8     0.79 1.1e-06
## 5            6     0.41 2.9e-06
## 6            8     0.94 4.2e-06
## 7           10     1.79 1.1e-05
## 8            4     0.15 1.4e-05
## 9           27    11.81 1.7e-05
## 10          15     4.36 2.3e-05
## [1] "diffusion map @@@dimension: 5"
##         GO.ID                                        Term Annotated
## 1  GO:0044130 negative regulation of growth of symbion...        12
## 2  GO:0044146 negative regulation of growth of symbion...        12
## 3  GO:0044126    regulation of growth of symbiont in host        13
## 4  GO:0044144 modulation of growth of symbiont involve...        13
## 5  GO:0044110    growth involved in symbiotic interaction        15
## 6  GO:0044116 growth of symbiont involved in interacti...        15
## 7  GO:0044117                  growth of symbiont in host        15
## 8  GO:0006935                                  chemotaxis       183
## 9  GO:0042330                                       taxis       185
## 10 GO:0050832                  defense response to fungus        12
##    Significant Expected classic
## 1            4     0.09 1.6e-06
## 2            4     0.09 1.6e-06
## 3            4     0.10 2.3e-06
## 4            4     0.10 2.3e-06
## 5            4     0.12 4.3e-06
## 6            4     0.12 4.3e-06
## 7            4     0.12 4.3e-06
## 8            8     1.42 8.2e-05
## 9            8     1.44 8.8e-05
## 10           3     0.09 9.4e-05
## [1] "diffusion map @@@dimension: 6"
##         GO.ID                                        Term Annotated
## 1  GO:0019886 antigen processing and presentation of e...        12
## 2  GO:0002495 antigen processing and presentation of p...        15
## 3  GO:0002504 antigen processing and presentation of p...        15
## 4  GO:0002478 antigen processing and presentation of e...        22
## 5  GO:0019884 antigen processing and presentation of e...        27
## 6  GO:0034341                response to interferon-gamma        38
## 7  GO:0048002 antigen processing and presentation of p...        39
## 8  GO:0034097                        response to cytokine       294
## 9  GO:0019882         antigen processing and presentation        65
## 10 GO:0002694          regulation of leukocyte activation       246
##    Significant Expected classic
## 1            4     0.03 2.8e-08
## 2            4     0.04 7.6e-08
## 3            4     0.04 7.6e-08
## 4            4     0.06 4.0e-07
## 5            4     0.08 9.5e-07
## 6            4     0.11 3.9e-06
## 7            4     0.11 4.3e-06
## 8            7     0.85 1.5e-05
## 9            4     0.19 3.4e-05
## 10           6     0.71 6.1e-05
## [1] "diffusion map @@@dimension: 7"
##         GO.ID                                        Term Annotated
## 1  GO:0002478 antigen processing and presentation of e...        22
## 2  GO:0019884 antigen processing and presentation of e...        27
## 3  GO:0019886 antigen processing and presentation of e...        12
## 4  GO:0002495 antigen processing and presentation of p...        15
## 5  GO:0002504 antigen processing and presentation of p...        15
## 6  GO:0048002 antigen processing and presentation of p...        39
## 7  GO:0006952                            defense response       612
## 8  GO:0019882         antigen processing and presentation        65
## 9  GO:0034341                response to interferon-gamma        38
## 10 GO:0006955                             immune response       585
##    Significant Expected classic
## 1            5     0.07 6.2e-09
## 2            5     0.09 1.9e-08
## 3            4     0.04 4.2e-08
## 4            4     0.05 1.2e-07
## 5            4     0.05 1.2e-07
## 6            5     0.13 1.3e-07
## 7           11     1.97 1.6e-06
## 8            5     0.21 1.8e-06
## 9            4     0.12 6.0e-06
## 10          10     1.88 8.6e-06
## [1] "diffusion map @@@dimension: 8"
##         GO.ID                                        Term Annotated
## 1  GO:0019886 antigen processing and presentation of e...        12
## 2  GO:0002495 antigen processing and presentation of p...        15
## 3  GO:0002504 antigen processing and presentation of p...        15
## 4  GO:0002478 antigen processing and presentation of e...        22
## 5  GO:0019884 antigen processing and presentation of e...        27
## 6  GO:0048002 antigen processing and presentation of p...        39
## 7  GO:0019882         antigen processing and presentation        65
## 8  GO:0034341                response to interferon-gamma        38
## 9  GO:0050868    negative regulation of T cell activation        55
## 10 GO:0002579 positive regulation of antigen processin...        10
##    Significant Expected classic
## 1            4     0.02 5.3e-09
## 2            4     0.03 1.4e-08
## 3            4     0.03 1.4e-08
## 4            4     0.04 7.7e-08
## 5            4     0.05 1.8e-07
## 6            4     0.08 8.4e-07
## 7            4     0.13 6.7e-06
## 8            3     0.07 5.2e-05
## 9            3     0.11 1.6e-04
## 10           2     0.02 1.6e-04
## [1] "diffusion map @@@dimension: 9"
##         GO.ID                                        Term Annotated
## 1  GO:0042108 positive regulation of cytokine biosynth...        35
## 2  GO:0001818 negative regulation of cytokine producti...       108
## 3  GO:0042035 regulation of cytokine biosynthetic proc...        51
## 4  GO:0042089               cytokine biosynthetic process        57
## 5  GO:0042107                  cytokine metabolic process        57
## 6  GO:0044130 negative regulation of growth of symbion...        12
## 7  GO:0044146 negative regulation of growth of symbion...        12
## 8  GO:0042036 negative regulation of cytokine biosynth...        13
## 9  GO:0044126    regulation of growth of symbiont in host        13
## 10 GO:0044144 modulation of growth of symbiont involve...        13
##    Significant Expected classic
## 1            3     0.08 6.4e-05
## 2            4     0.25 9.3e-05
## 3            3     0.12 2.0e-04
## 4            3     0.13 2.8e-04
## 5            3     0.13 2.8e-04
## 6            2     0.03 3.2e-04
## 7            2     0.03 3.2e-04
## 8            2     0.03 3.8e-04
## 9            2     0.03 3.8e-04
## 10           2     0.03 3.8e-04
## [1] "diffusion map @@@dimension: 10"
##        GO.ID                    Term Annotated Significant Expected
## 1 GO:0048821 erythrocyte development        25           2     0.03
##   classic
## 1 0.00049
tsne_diffmap = Rtsne(dif@eigenvectors[,])
tsne_diffmap1 = Rtsne(dif@eigenvectors[,],dim=1)

tsne_ph = Rtsne(log10(ph_data))
tsne_ph1 = Rtsne(log10(ph_data),dim=1)

plot(tsne_diffmap$Y[,1], tsne_diffmap$Y[,2])

plot(tsne_ph$Y[,1], tsne_ph$Y[,2])

plot(tsne_diffmap1$Y, tsne_ph1$Y)

tsne_df = data.frame(transcriptome_dim1 = tsne_diffmap$Y[,1], 
                     transcriptome_dim2 = tsne_diffmap$Y[,2],
                     phenotype_dim1 = tsne_ph$Y[,1], 
                     phenotype_dim2 = tsne_ph$Y[,2],
                     transcriptome_1d = tsne_diffmap1$Y[,1], 
                     phenotype_1d = tsne_ph1$Y[,1])


combined_df = cbind(tsne_df,log10(ph_data),t(log2(expr_data+1)))
ggplot(combined_df,aes(x=transcriptome_1d,y=phenotype_1d,col=Rsad2))+geom_point()

write.csv(combined_df,file="shalin_192_pca_diff_new.csv", quote = FALSE)
diff_genes = c()
for(i in 1:10){diff_genes = c(diff_genes,rownames(dif_GO_list$DE_genes[[i]]))}
DE_expr = expr_data[rownames(expr_data) %in% diff_genes,]
dim(DE_expr)
## [1] 508 187
heatmap.2(log2(DE_expr+1),trace="none")

tsne_diffmap_DE = Rtsne(cor(log2(DE_expr+1)))
tsne_diffmap_DE1 = Rtsne(cor(log2(DE_expr+1)),dim=1)
plot(tsne_diffmap_DE$Y[,1], tsne_diffmap_DE$Y[,2])

plot(tsne_diffmap_DE1$Y, tsne_ph1$Y)

database = "haemopedia"
immgen_samples <- read.delim(paste0("~/Downloads/",database,"_samples.txt"), stringsAsFactors=FALSE)
immgen_probes <- read.delim(paste0("~/Downloads/",database,"_probes.txt"), header=FALSE, stringsAsFactors=FALSE)
immgen_expression <- read.delim(paste0("~/Downloads/",database,"_expression.txt"), stringsAsFactors=FALSE)
library('biomaRt')
mart <- useDataset("mmusculus_gene_ensembl", useMart("ensembl"))
G_list <- getBM(filters= "ensembl_gene_id", attributes= c("ensembl_gene_id", "external_gene_name", "description"),values=immgen_probes$V2 ,mart=mart)
immgen_probes = immgen_probes[immgen_probes$V2 %in% G_list$ensembl_gene_id,]
G_list = G_list[match(immgen_probes$V2, G_list$ensembl_gene_id),]
immgen_probes$external_gene_name = G_list$external_gene_name
immgen_expression = immgen_expression[immgen_expression$X %in% immgen_probes$V1,]
immgen_probes = immgen_probes[immgen_probes$V1 %in% immgen_expression$X,]
immgen_probes = immgen_probes[match(immgen_expression$X, immgen_probes$V1),]
immgen_expression$gene_id = immgen_probes$external_gene_name
immgen_expression = immgen_expression[!duplicated(immgen_expression$gene_id),]
rownames(immgen_expression) = immgen_expression$gene_id
immgen_expression = immgen_expression[,!(colnames(immgen_expression) %in% c("X","gene_id"))]
dim(immgen_expression)
## [1] 19180   169
table(immgen_samples$cell_lineage)
## 
##                  B Cell Lineage                Basophil Lineage 
##                              15                               2 
##          Dendritic Cell Lineage              Eosinophil Lineage 
##                              12                               6 
##             Erythrocyte Lineage              Macrophage Lineage 
##                              17                              11 
##               Mast Cell Lineage           Megakaryocyte Lineage 
##                               2                               9 
##      Multi Potential Progenitor              Neutrophil Lineage 
##                              17                               5 
##                 NK Cell Lineage Restricted Potential Progenitor 
##                               2                              28 
##                  T Cell Lineage 
##                              43
immgen_samples$sampleId = gsub("-",".",immgen_samples$sampleId)
#SC_list = immgen_samples[immgen_samples$cell_lineage == "Stem Cells", "sampleId"]
SC_list = immgen_samples$sampleId
sub_immgen_expression = immgen_expression[rownames(immgen_expression) %in% rownames(DE_expr), colnames(immgen_expression) %in% SC_list]
sub_DE_expr = DE_expr[rownames(DE_expr) %in% rownames(sub_immgen_expression),]
sub_DE_expr = sub_DE_expr[!duplicated(rownames(sub_DE_expr)),]
sub_DE_expr = sub_DE_expr[order(rownames(sub_DE_expr)),]
sub_immgen_expression = sub_immgen_expression[order(rownames(sub_immgen_expression)),]
p.val_mat = c()
for (i in 1:ncol(sub_immgen_expression))
{
  p.val_vec = apply(sub_DE_expr, 2, function(x){
  cor.test(x,sub_immgen_expression[,i],
         method = "spearman",
         alternative = "greater")$p.value})
  p.val_mat = rbind(p.val_mat,-log10(p.val_vec))
}
rownames(p.val_mat) = colnames(sub_immgen_expression)

hmcol<-colorRampPalette(c("blue", "white","red"))(n = 299)
heatmap.2(p.val_mat,trace="none",
          col=hmcol,
          scale="column",
          density.info="none",
          key=FALSE)

tsne_immgen = Rtsne(cor(p.val_mat))
plot(tsne_immgen$Y[,1], tsne_immgen$Y[,2])